Rank Pooling Approach for Wearable Sensor-Based ADLs Recognition
Rank Pooling Approach for Wearable Sensor-Based ADLs Recognition
复制标题
DOI：
10.3390/s20123463
复制
发表时间：
2020-06-01
期刊：
影响因子：
3.9
通讯作者：
Grzegorzek, Marcin
中科院分区：
文献类型：
--
作者：
Nisar, Muhammad Adeel;Shirahama, Kimiaki;Grzegorzek, Marcin
本文讨论了基于可穿戴设备的日常生活活动（ADL）的识别，这些活动由几个具有时间依赖性的重复和并发的短动作组成。直接使用传感器数据来识别这些长期复合活动是不可能的，因为相同ADL的两个示例（数据序列）导致很大程度上不同的感觉数据。然而，它们可能在更语义和更有意义的短期行为方面是相似的。因此，我们提出了一个两级层次模型识别的日常生活活动。首先，检测原子活动，并在较低级别上生成其概率分数。其次，我们处理原子活动的时间转换使用时间池方法，秩池。这使我们能够在我们模型的更高级别上对原子活动的概率分数的排序进行编码。与其他常用的技术相比，排名合并导致结果改善5-13%。我们还为我们的实验产生了61个原子和7个复合活动的大数据集。
This paper addresses wearable-based recognition of Activities of Daily Living (ADLs) which are composed of several repetitive and concurrent short movements having temporal dependencies. It is improbable to directly use sensor data to recognize these long-termcomposite activitiesbecause two examples (data sequences) of the same ADL result in largely diverse sensory data. However, they may be similar in terms of more semantic and meaningful short-termatomic actions. Therefore, we propose a two-level hierarchical model for recognition of ADLs. Firstly, atomic activities are detected and their probabilistic scores are generated at the lower level. Secondly, we deal with the temporal transitions of atomic activities using a temporal pooling method,rank pooling. This enables us to encode the ordering of probabilistic scores for atomic activities at the higher level of our model. Rank pooling leads to a 5-13% improvement in results as compared to the other popularly used techniques. We also produce a large dataset of 61 atomic and 7 composite activities for our experiments.